expense-management – Other skill for AI agents
Expense claim register: claim id, employee and department, amount and tax, approver and level, category, cost centre, budget line, receipt flag and status. Use for claim approvals.
Install the expense-management skill with one command
Pick the tool you use, copy the command and paste it in your terminal. The skill lands in that tool's skills folder and is ready in your next session.
Claude Code
mkdir -p ~/.claude/skills && curl -fsSL https://skill.dn1nguoi.com/z/expense-management-eb967.tgz | tar xz -C ~/.claude/skills
Call it in Claude Code: /expense-management – then describe the task you want done.
Codex
mkdir -p ~/.codex/skills && curl -fsSL https://skill.dn1nguoi.com/z/expense-management-eb967.tgz | tar xz -C ~/.codex/skills
Call it in Codex: $expense-management – then describe the task you want done.
Hermes Agent
mkdir -p ~/.hermes/skills && curl -fsSL https://skill.dn1nguoi.com/z/expense-management-eb967.tgz | tar xz -C ~/.hermes/skills
Call it in Hermes Agent: /expense-management – then describe the task you want done.
DeepSeek
mkdir -p ~/.deepcode/skills && curl -fsSL https://skill.dn1nguoi.com/z/expense-management-eb967.tgz | tar xz -C ~/.deepcode/skills
Call it in DeepSeek: /expense-management – then describe the task you want done.
SKILL.md content
Expense Management
What it is: Claims.
Overview
Works out the smallest useful Expense Management setup for the business in front of it, then
builds it only when asked. The default output is a short recommendation, not a
spreadsheet. Artifacts - CSV, SQL DDL, JSON Schema, Notion mapping - are produced on
request, from one field list so they cannot drift apart.
Layer: Layer 4: Manage. Fits: Starter stage. Table code: n/a.
When to Use This Skill
- expense tracker
- expense claim form
- reimbursement tracker
- spend claim database
Also use it when the user says "claims", or describes the same process happening in a
spreadsheet, a document or someone inboxes.
Do not use it for: payroll calculation, tax filing, or legal advice. This skill produces
empty templates only - it never holds or processes real employee or customer data.
How It Works
Follow the shared execution contract. The module-specific rules below define only domain fields, decisions, calculations, and safety constraints.
Step 1 - Identify intent
Read the request and pick the intent before asking anything.
- "set up" or "build" or "create" -> the user wants artifacts; go to Step 2.
- "our process is ..." or "it is in a sheet" -> the user wants to move an existing process; capture it, then Step 2.
- "is this right" or "review" or "audit" -> the user wants a check, not a build; answer from what they share.
- "how do I ..." -> advice question; answer directly and offer the build only if it helps.
Ask only if this is the highest-value missing fact; otherwise proceed without an opener:
> Q: What is your expense approval limit?
Step 2 - Ask only what is missing
Skip anything the user already answered, in any earlier message. Ask the rest one at a
time, and stop as soon as the remaining answers would not change the output.
- Policy - Approval limit per claim? / Receipt required above? / Category rules?
- Flow - Who approves first? / Finance second? / Reimbursed how?
- Data - Tax claimed? / Project or cost centre? / Currency?
- Current process - How do you track claims now? / Spreadsheet or app? / What gets rejected?
- Outcome - What do you need? / A claim form, approvals or reconciliation?
Never invent an answer. If the user does not know, record it as unknown and carry on.
Step 3 - Hold the internal context
Hold the answers in this shape. It stays internal - it is not shown to the user unless
they ask, and it never carries a value the user did not give.
module: expense-management
intent: null # setup | advice | review | fix | build | convert | export
scale: null # Starter | Growth | Scale, only if the answer changes it
areas:
"Policy": null
"Flow": null
"Data": null
"Current process": null
"Outcome": null
requested_outputs: [] # csv | sql | json | notion | xlsx - requested formats only
confirmed_facts: [] # only what the user actually said
open_questions: [] # the unanswered ones, in the order worth askingStep 4 - Recommend the smallest workflow
If an artifact was requested, build it after resolving essential missing facts. Otherwise give a short recommendation and offer the relevant artifact.
Recommended approach: Build a claim form that forces receipt and amount, then route by limit. Keep the finance reconciliation as a separate monthly step.
Why this one: Most expense problems are missing receipts and unclear limits, both of which can be enforced at data entry rather than at approval.
Workflow: Claim submitted → Manager approval → Finance check → Reimbursement → Monthly reconciliation
Step 5 - Build only on request
Once the user asks for it, derive the fields from the confirmed context and emit the
requested artifacts. For machine-readable text, keep prose outside the data; for files,
provide a usable link. Report material validation failures or limitations separately.
**A selected Notion output is rendered by notion-manual-import, so route the
Notion step there.** When the user selects Notion, hand that step to
@notion-manual-import: it holds the CSV, the property
mapping, the import steps and the verification checklist, and it renders the Field
Reference below instead of defining a table of its own. Do not restate the mapping
here and do not improvise the import steps. Manual CSV and mapping outputs need no
connection. For requested workspace changes, follow the shared contract: verify actual
tool access and the target before writing. A user saying "connected" is not tool evidence.
Never ask for a Notion password or token.
For an Excel-compatible CSV, use UTF-8 with a byte order mark so Excel opens the
text correctly. A CSV is not an .xlsx workbook; create .xlsx only when the user
requests a workbook.
A CSV carries no types, so after it, name the columns
that need a number, date or currency format applied.
Expense Claim,Amount,Tax Amount,Approver,Approval Level,Category,Currency,Date of Expense,Department,Employee Name,Expense ID,Notes,Project/Cost Centre,Budget Line,Receipt Attached,Reimbursement Date,Status,Submission Date
EXP-2026-014,45000.00,8100.00,Sneha Iyer,Manager,General,INR,2026-01-15,Delivery,Aarav Sharma,,Synthetic approved claim awaiting reimbursement.,CC-200 Website Redesign,BL-114 Travel,TRUE,,Approved,2026-01-15CREATE TABLE expense_management (
expense_claim VARCHAR(255),
amount NUMERIC(14,2) NOT NULL,
tax_amount NUMERIC(14,2) NOT NULL,
approver VARCHAR(255),
approval_level VARCHAR(100) NOT NULL,
category VARCHAR(100) NOT NULL,
currency VARCHAR(255),
date_of_expense DATE NOT NULL,
department VARCHAR(255),
employee_name VARCHAR(255),
expense_id SERIAL PRIMARY KEY,
notes TEXT,
project_cost_centre VARCHAR(255),
budget_line VARCHAR(255),
receipt_attached BOOLEAN NOT NULL,
reimbursement_date DATE,
status VARCHAR(100) NOT NULL,
submission_date DATE NOT NULL,
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
CREATE INDEX idx_expense_management_status ON expense_management (status);{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"title": "Expense Management",
"type": "object",
"additionalProperties": false,
"properties": {
"Expense Claim": { "type": "string" },
"Amount": { "type": "number" },
"Tax Amount": { "type": "number" },
"Approver": { "type": "string" },
"Approval Level": { "type": "string" },
"Category": { "type": "string" },
"Currency": { "type": "string" },
"Date of Expense": { "type": "string", "format": "date" },
"Department": { "type": "string" },
"Employee Name": { "type": "string" },
"Expense ID": { "type": "integer" },
"Notes": { "type": "string" },
"Project/Cost Centre": { "type": "string" },
"Budget Line": { "type": "string" },
"Receipt Attached": { "type": "boolean" },
"Reimbursement Date": { "type": "string", "format": "date" },
"Status": { "type": "string" },
"Submission Date": { "type": "string", "format": "date" }
},
"required": [
"Amount",
"Tax Amount",
"Approval Level",
"Category",
"Date of Expense",
"Receipt Attached",
"Status",
"Submission Date"
]
}| CSV column | Notion property | Set after import |
|---|---|---|
| Expense Claim | Title | Use as the database title |
| Amount | Number (format: currency) | Convert to Number, set format to Currency |
| Tax Amount | Number (format: currency) | Convert to Number, set format to Currency |
| Approver | Text | Leave as Text |
| Approval Level | Select (add options after import) | Convert to Select, add options: "Manager", "Finance", "Owner", "Auto Approved" |
| Category | Select (add options after import) | Convert to Select, add options: "General", "Operations", "Finance", "People", "Compliance" |
| Currency | Text | Leave as Text |
| Date of Expense | Date | Convert to Date |
| Department | Text | Leave as Text |
| Employee Name | Text | Leave as Text |
| Expense ID | Text (preserve source ID) | Keep imported IDs as Text; optionally add a separate Unique ID property |
| Notes | Text | Leave as Text |
| Project/Cost Centre | Text | Leave as Text |
| Budget Line | Text | Leave as Text |
| Receipt Attached | Checkbox | Convert to Checkbox |
| Reimbursement Date | Date | Convert to Date |
| Status | Select (add options after import) | Convert to Select, add options: "Draft", "Submitted", "Approved", "Reimbursed", "Rejected" |
| Submission Date | Date | Convert to Date |The rows above are documentation examples only. Emit empty templates unless the user explicitly requests examples. Money stays currency, dates stay date,
and anything pointing at another table stays relation.
Field Reference
| # | Field | Type | SQL | JSON Schema | Notion | CSV example |
|---:|---|---|---|---|---|---|
| 1 | Expense Claim | text | `VAR
… (full content is in the download package)
Related skills
- explain-like-socrates – Explains concepts using Socratic-style dialogue. Use when the user asks to explain…
- expo-dev-client – Build Expo app for development
- expo-examples – Expo's official example projects — the expo/examples repo of ~70 `with-*` integrations…
- fact-check-x-unified – Fact-Check-X 流程编排能力,依次组织各方答案汇总、各方答案聚合(未核验)、权威核验后的最终答案和各方答案测评,生成可打开、可审计、可迁移的阶段产物与完整报告包。
- faf-context – Get your project to 100% ✪ AI-readiness, fast — the AI auto-detects your stack and only…
- faf-wizard – Done-for-you .faf generator. One-click AI context for any project - new, legacy, or…
- fal-audio – Text-to-speech and speech-to-text using fal.ai audio models
- roadmap-communicator – Use when preparing roadmap narratives, release notes, changelogs, or stakeholder updates…